gcpGoogle Cloud incident history
A full searchable archive of Google Cloud Service Health events and resolved outages.
Sourced live from the official Google Cloud Service Health dashboard. How we verify.
Active now
0
Tracked incidents
8
Products affected
5
Avg resolution
3d 34m
Showing 1-8 of 8 incidents
Network traffic to Google Cloud originating from Delhi, Chennai, Mumbai and surrounding areas is experiencing intermittent periods of elevated latency and possible packet loss.
Network traffic to Google Cloud originating from Delhi, Chennai, Mumbai and surrounding areas is experiencing intermittent periods of elevated latency and possible packet loss.
Vertex AI Gemini API customers experienced increased error rates when accessing the global endpoint.
Vertex AI Gemini API customers experienced increased error rates when accessing the global endpoint.
Global Google Cloud outage from an invalid automated policy update
A malformed automated quota policy update to Service Control - the component that authorizes API requests - lacked error handling and hit a null pointer, crash-looping the binary and returning elevated 5xx errors across many Google Cloud services worldwide. Impact lasted just under three hours; us-central1 was worst-hit (~2h35m).
Water leak and fire force an extended shutdown of the europe-west9 (Paris) region
A cooling-system water pump failure, followed by a fire, in a europe-west9 (Paris) data center forced an emergency shutdown of the europe-west9-a zone and part of europe-west9-c. Compute Engine and dependent services were unavailable for an extended, multi-day recovery.
Cooling failure powers down part of a europe-west2 (London) zone during the heatwave
During a record UK heatwave, a simultaneous failure of multiple redundant cooling systems in a europe-west2 (London) data center left it unable to hold a safe temperature. Google powered down part of europe-west2-a, terminating roughly 35% of the zone’s Compute Engine VMs to prevent equipment damage.
Global 404 errors for external HTTP(S) Load Balancing
A bug in the configuration pipeline that propagates rules to Google’s external HTTP(S) Load Balancing (GCLB) caused affected sites to return 404 errors, with knock-on impact to App Engine, Cloud Functions, Cloud Run, and Apigee. Total impact was about 1 hour 53 minutes; a rollback to the last-known-good config resolved it.
Global authentication failures across Google services
An automated storage-quota system reduced capacity for the central User ID service (which issues the OAuth tokens/cookies used to sign in), causing authentication to fail for services that require login - including Google Cloud, Gmail, and YouTube - for roughly 45 minutes.
Network congestion across multiple US regions
A configuration change intended for a small number of servers in one region was incorrectly applied to a much larger set across several US regions, dropping more than half of their network capacity and causing severe congestion in parts of us-east, us-central, and us-west for about four hours.